预览加载中,请您耐心等待几秒...
1/7
2/7
3/7
4/7
5/7
6/7
7/7

在线预览结束,喜欢就下载吧,查找使用更方便

如果您无法下载资料,请参考说明:

1、部分资料下载需要金币,请确保您的账户上有足够的金币

2、已购买过的文档,再次下载不重复扣费

3、资料包下载后请先用软件解压,在使用对应软件打开

ComputerEngineeringandApplications计算机工程与应用201753(17)153基于多传感器融合的动态手势识别研究分析用马正华1李雷2乔玉涛2戎海龙3曹海婷2MAZhenghua1LILei2QIAOYutao2RONGHailong3CAO应Haiting2与1.常州大学研究生部江苏常州2131642.常州大学信息科学与工程学院数理学院程江苏常州2131643.常州大学城市轨道交通学院江苏常州213164rg1.GraduateDivisionChangzhouUniversity工ChangzhouJiangsu213164oChina2.SchoolofInformationScience&EngineeringSchoolofMathematicsj.&PhysicsChangzhouUniversityChangzhouJiangsu213164China机a3.SchoolofUrban算RailTransitChangzhouUniversity.cChangzhoueJiangsu213164ChinaMAZhenghua计LILeiQIAOYutaoetal.wDynamicgesturerecognitionresearchandanalysisbasedonmulti-sensorfusion.ComputerEngineeringandwApplications201753(17):153-159.Abstract:Thispaperstudieswusingthreekindsofsensors(surfaceelectromyographygyroscopeandaccelerometer)singnalcharacteristicsforinformationfusion.Thepurposeistoimprovethetypesandaccuracyofrecognizabledynamichandgestures.Dynamichandgesturesaredividedintothreeelements:handshapegesturestowardsandtrajectory.ThethreeelementsarerespectivelyrepresentedbysurfaceElectromyogramsignal(sEMG)Gyroscopesignal(GYRO)andAcceler-ationsignal(ACC).Multi-streamingHMMsareusedforpatternrecognitionofdynamichandgestures.Intherecognitionexperimentsthatcontainfivemotiontrajectoriesandsixstatichandshapestheresultsshowthatthismethodcaneffec-tivelyidentifydynamichandgesturesfromthecontinuoussignals.Theglobalaveragerecognitionrateobtainedfromthecompositeuseofthreekindsofsensorsishigherthan92%.Itissignificantlyhigherthantheaveragerecognitionratethatobtainedfromthecombinationofanytwosensorsorsinglesensoronly.Experimentalresultsshowthat